no code implementations • 12 Jun 2023 • Matthieu Armando, Laurence Boissieux, Edmond Boyer, Jean-Sebastien Franco, Martin Humenberger, Christophe Legras, Vincent Leroy, Mathieu Marsot, Julien Pansiot, Sergi Pujades, Rim Rekik, Gregory Rogez, Anilkumar Swamy, Stefanie Wuhrer
This work presents 4DHumanOutfit, a new dataset of densely sampled spatio-temporal 4D human motion data of different actors, outfits and motions.
Inspired by properties of semantic segmentation, in this paper we investigate how to leverage robust image segmentation in the context of privacy-preserving visual localization.
In order to investigate the consequences for visual localization, this paper focuses on understanding the role of image retrieval for multiple visual localization paradigms.
In this paper, we introduce 5 new indoor datasets for visual localization in challenging real-world environments.
Experimental results conducted on three diverse benchmarks demonstrate excellent speed estimation accuracy that could enable the wide use of CCTV cameras for traffic analysis, even in challenging conditions where state-of-the-art methods completely fail.
This paper focuses on understanding the role of image retrieval for multiple visual localization tasks.
To demonstrate this, we present a versatile pipeline for visual localization that facilitates the use of different local and global features, 3D data (e. g. depth maps), non-vision sensor data (e. g. IMU, GPS, WiFi), and various processing algorithms.
This paper introduces an updated version of the well-known Virtual KITTI dataset which consists of 5 sequence clones from the KITTI tracking benchmark.
We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness.
Ranked #2 on Camera Localization on Aachen Day-Night benchmark
In this work, we argue that salient regions are not necessarily discriminative, and therefore can harm the performance of the description.
This paper presents an overview of the evolution of local features from handcrafted to deep-learning-based methods, followed by a discussion of several benchmarks and papers evaluating such local features.
However, major questions concerning quality and usefulness of test data for CV evaluation are still unanswered.
This checklist can be used to evaluate existing test datasets by quantifying the amount of covered hazards.